Skip to main content

​
The Agent Runtime Intelligence Layer

cascadeflow is infrastructure that sits inside AI agent execution and continuously optimizes outcomes across business and technical constraints in real time. This is not another model router. It is a decision system inside the agent loop. Every model call, tool call, and sub-agent handoff can be measured, scored, and steered — where cost, delay, and failure actually happen.

Get Started

Install, observe, enforce, and ship to production in minutes.

Why cascadeflow

The business case for inside-the-loop agent intelligence.

​
Install

pip install cascadeflow

import cascadeflow

cascadeflow.init(mode="observe")
# Every OpenAI and Anthropic SDK call is now tracked — zero code changes.

​
What Makes This Different

External Proxycascadeflow
Where it runsHTTP boundaryInside the agent loop
What it seesRequest/response pairsStep count, budget, tool history, quality, domain, business context
What it optimizesCostCost + latency + quality + budget + compliance + energy
What it doesObservesallow, switch_model, deny_tool, stop
Latency overhead40-60ms per call<1ms in-process
In 10-step agent loop400-600ms added~0ms added

​
Three Lines to Govern Any Agent

import cascadeflow
cascadeflow.init(mode="observe")
# All LLM calls tracked. No blocking, no changes.

​
Six Dimensions, One Decision

Every agent step is scored across six dimensions simultaneously:
DimensionWhat it controlsExample
CostUSD per LLM call from pricing tableBudget cap of $0.50 per run
LatencyWall-clock milliseconds per callMax 2000ms per call
QualityModel quality priors for routing60% weight on quality KPI
BudgetCumulative spend tracking and capsPer-user daily limits
ComplianceModel allowlists per regulationGDPR: only approved models
EnergyCompute-intensity coefficientsCarbon-aware model selection

​
Works With Every Major Framework

FrameworkPythonTypeScriptType
LangChain / LangGraphcascadeflow[langchain]@cascadeflow/langchainCallback handler
OpenAI Agents SDKcascadeflow[openai-agents]—ModelProvider
CrewAIcascadeflow[crewai]—llm_hooks
Google ADKcascadeflow[google-adk]—BasePlugin
n8n—@cascadeflow/n8n-nodes-cascadeflowCommunity node
Vercel AI SDK—@cascadeflow/vercel-aiMiddleware

​
Explore

Agent Harness

Configure budget, compliance, KPI, and energy controls.

Agent Loop

How cascadeflow operates inside multi-step agent execution.

Examples

42+ Python and 33+ TypeScript examples on GitHub.

Integrations

LangChain, OpenAI Agents, CrewAI, Google ADK, n8n, Vercel AI.

API Reference

Full Python and TypeScript API documentation.

For Coding Agents

Canonical facts, repo map, and implementation entry points.